Few-Shot Learning in Wireless Networks: A Meta-Learning Model-Enabled Scheme

Restricted by the data sensing capability, it is challenging for a single user to generate high-quality deep learning models based on its collected few-shot data samples. Metalearning provides a promising paradigm to make full use of historical data at the base stations to improve the performance of few-shot learning tasks. However, it is a dilemma to balance the performance and the communication costs of meta-learning. In this paper, we studied the design of few-shot learning in wireless networks. First, a meta-learning model-based scheme is designed to adapt the few-shot learning tasks, and a multicastingbased model transmission scheme is proposed. Second, a coalition formation-based model selection scheme is designed to achieve a sophisticated tradeoff between the performance and the communication costs of meta-learning. Finally, the simulation results are provided, which show that our proposed scheme can improve the model accuracy performance with low communication costs.

Automated summary

In this paper, the design of few-shot learning in wireless networks was studied, proposing a meta-learning model-based scheme and a coalition formation-based model selection scheme. The simulation results show that the proposed scheme can improve model accuracy performance with low communication costs.